Security Audit
Ethical Hacking Methodology
github.com/davila7/claude-code-templatesTrust Assessment
Ethical Hacking Methodology received a trust score of 10/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 8 findings: 3 critical, 3 high, 1 medium, and 1 low severity. Key findings include File read + network send exfiltration, Sensitive path access: SSH key/config, Network egress to untrusted endpoints.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 10/100, indicating areas for improvement.
Last analyzed on February 12, 2026 (commit 458b1186). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings8
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | File read + network send exfiltration SSH key/config file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | cli-tool/components/skills/security/ethical-hacking-methodology/SKILL.md:275 | |
| CRITICAL | Skill contains highly destructive disk wipe command The skill includes a `dd` command example that, if executed, can overwrite an entire disk, leading to irreversible data loss. This poses a critical risk if the AI agent or a user is prompted to execute it without understanding its destructive potential, especially given the context of installing an OS. Remove or heavily redact highly destructive commands. If absolutely necessary for educational context, add explicit, prominent warnings about the command's destructive nature and the requirement for a safe, isolated environment (e.g., virtual machine) for practice. | LLM | SKILL.md:207 | |
| CRITICAL | Skill contains command to create persistent backdoor The skill provides an example of modifying `/etc/crontab` to establish a persistent backdoor. Execution of this command could grant unauthorized, persistent access to a system. This is a critical security risk if the AI agent or a user is prompted to execute it. Remove or heavily redact commands that create persistent unauthorized access. If necessary for educational purposes, provide strong warnings about the ethical and legal implications, and emphasize execution only in controlled, isolated environments. | LLM | SKILL.md:167 | |
| HIGH | Sensitive path access: SSH key/config Access to SSH key/config path detected: '~/.ssh/authorized_keys'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | cli-tool/components/skills/security/ethical-hacking-methodology/SKILL.md:275 | |
| HIGH | Skill contains command to read sensitive system files The skill includes an example of using `cat /etc/passwd` to read a sensitive system file. If executed in an inappropriate context, this could lead to the disclosure of user account information. Remove or heavily redact commands that access sensitive system files. If included for educational purposes, provide clear warnings about the privacy implications and the need for authorization. | LLM | SKILL.md:150 | |
| HIGH | Skill provides detailed examples of offensive security tool usage The skill extensively details the usage of powerful offensive security tools such as Metasploit, Hydra, SQLMap, Nmap, and Nikto. While presented in an ethical hacking context, the detailed instructions for these tools could be misused by an AI agent or a user to perform unauthorized or illegal activities if not accompanied by strict ethical guidelines and authorization requirements. Emphasize ethical guidelines and legal requirements more prominently throughout the sections detailing offensive tool usage. Add explicit disclaimers that these tools should only be used with express written permission on authorized targets. Consider adding a 'WARNING: Illegal Use' disclaimer next to each such command. | LLM | SKILL.md:129 | |
| MEDIUM | Network egress to untrusted endpoints HTTP request to raw IP address Review all outbound network calls. Remove connections to webhook collectors, paste sites, and raw IP addresses. Legitimate API calls should use well-known service domains. | Manifest | cli-tool/components/mcps/devtools/figma-dev-mode.json:4 | |
| LOW | Covert behavior / concealment directives Multiple zero-width characters (stealth text) Remove hidden instructions, zero-width characters, and bidirectional overrides. Skill instructions should be fully visible and transparent to users. | Manifest | cli-tool/components/mcps/devtools/jfrog.json:4 |
Scan History
Embed Code
[](https://skillshield.io/report/71b859ecd689a33f)
Powered by SkillShield